Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    science, medical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rub
    -0.78
     rubbed
    -0.59
     def
    -0.54
     m
    -0.49
    rub
    -0.49
     f
    -0.49
     F
    -0.49
     t
    -0.49
     de
    -0.47
     var
    -0.47
    POSITIVE LOGITS
     Jefus
    1.07
     Eſ
    1.02
     myſelf
    0.96
     becauſe
    0.94
     Anſ
    0.94
     Reſ
    0.93
     Efq
    0.93
     Majefty
    0.93
     greateſt
    0.92
     iſt
    0.91
    Act Density 0.047%

    No Known Activations